REVIEW 18 cited by
Large Language Model Guided Tree-of-Thought
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). The ToT technique is inspired by the human mind's approach for solving complex reasoning tasks through trial and error. In this process, the human mind explores the solution space through a tree-like thought process, allowing for backtracking when necessary. To implement ToT as a software system, we augment an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. In order to solve a given problem, these modules engage in a multi-round conversation with the LLM. The memory module records the conversation and state history of the problem solving process, which allows the system to backtrack to the previous steps of the thought-process and explore other directions from there. To verify the effectiveness of the proposed technique, we implemented a ToT-based solver for the Sudoku Puzzle. Experimental results show that the ToT framework can significantly increase the success rate of Sudoku puzzle solving. Our implementation of the ToT-based Sudoku solver is available on GitHub: \url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.
Forward citations
Cited by 18 Pith papers
-
Understanding Reasoning from Pretraining to Post-Training
A joint scaling law: post-RL chess and math performance is predictable from pretraining loss, RL improvement rate grows with pretraining tokens, and RL both amplifies and discovers moves depending on difficulty.
-
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
A symplectic LQR layer inserted as an adapter into pretrained LLMs yields large gains on MATH-500, AMC and AIME by solving a latent optimal-control problem at inference time.
-
Hierarchical Domain Generalization
Over infinite domains, hierarchy-uniform domain generalization is impossible for every nontrivial hypothesis class; a length-generalization bound is a property of the length hierarchy, not a hierarchy-free guarantee.
-
Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction
A four-stage LLM framework that constructs, audits, and aggregates explicit causal chains outperforms prompting baselines on three context-free causal QA benchmarks.
-
TreeRL: LLM Reinforcement Learning with On-Policy Tree Search
TreeRL combines entropy-guided tree search with on-policy RL and tree-derived process rewards, reporting modest accuracy gains over chain sampling on math and code benchmarks.
-
OctoNav: Towards Generalist Embodied Navigation
OctoNav-R1, trained with SFT, GRPO, and online RL on the new OctoNav-Bench, achieves 19.4% overall success on mixed-instruction navigation, more than double the best baseline.
-
DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
DipSVD combines channel-weighted whitening with layer-wise compression ratios and reports better perplexity and accuracy than existing SVD-based LLM compression methods.
-
SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion
A multi-agent LLM system called SimuPanel simulates expert panel discussions with personas grounded in public academic sources, and a small evaluation suggests the full reasoning pipeline produces higher LLM-judged di...
-
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
VReST combines Monte Carlo tree search with a self-reward signal inside a vision-language model to get higher accuracy than CoT, ToT, or voting baselines on MathVista, MathVision, and CharXiv, while spending several t...
-
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search
Small language models achieve higher accuracy on math, coding, and logic benchmarks when their prompts contain LLM-generated reasoning blueprints and a per-model, per-task searched template.
-
Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
The ratio of agreement to disagreement between a small student model and an LLM correlates with the LLM's annotation accuracy across ten datasets and can heuristically select better models.
-
Project Patti: Why can You Solve Diabolical Puzzles on one Sudoku Website but not Easy Puzzles on another Sudoku Website?
A randomized Nishio solver's strategy-cycle count correlates strongly with website difficulty labels for four of five Sudoku sites, enabling a three-tier universal difficulty classification.
-
Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
In a small evaluation with PwC data, Llama-2-70b beats GPT models at the 'no compliance' class for IFRS reports, but the result is based on a single selected prompt and a 100-item sample, and the data/code are not released.
-
Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making
Asking an LLM 'could you be wrong?' after its answer surfaces its own biases, omitted evidence, and alternative perspectives in qualitative demonstrations on three tasks.
-
Introspection of Thought Helps AI Agents
INoT wraps prompts in XML-defined pseudo-code so an LLM simulates two debating agents internally, reporting better scores and lower tokens than seven baselines.
-
Few-shot text-based emotion detection
A system combining Gemini few-shot prompting with 600 examples achieved F1-macro 0.325 for Emakhuwa, 0.7546 for English, and 0.1727 for Mozambican Portuguese at SemEval-2025 Task 11.
-
Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy
A five-task case study shows DSPy prompt optimization can improve LLM accuracy on some tasks, notably contradiction detection (46.2% to 64.0%), but results vary and no code or data are released.
-
Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
A 4B-parameter model is claimed to explain its own reasoning through inverse attention analysis, but the paper offers no consistent evidence or artifacts.
Discussion (0). Sign in to comment.